Debiased Recommendation via Wasserstein Causal Balancing
ACM Transactions on Information Systems · 30.11.2025 · 43 (6) · 1-24
DOI: 10.1145/3725731 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 11.09.2025. Verfasst von Hao Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: National Natural Science Foundation of China, ARC.
Abstract (Originalsprache)
Recommendation systems are pivotal in improving user experience on various digital platforms. However, observational training data in recommendation systems introduce selection bias, which leads to a distributional discrepancy between training data and real-world scenarios, resulting in suboptimal performance. Current causal debiasing methods such as inverse propensity score and doubly robust rely on accurately estimated propensity scores, typically optimized through negative log-likelihood (NLL) minimization. However, recent studies have highlighted the limitations of this approach, as perfect NLL minimization may not adequately correct for selection bias. To address this issue, we propose Wasserstein Balancing Metric (WBM), a novel metric that measures and enhances the balancing capacity of propensity scores in causal debiasing methods by minimizing the Wasserstein discrepancy between reweighted populations. On the basis, we introduce IPS-WBM and DR-WBM, incorporating WBM as a regularizer in standard inverse propensity score and doubly robust estimators, which enhances causal balancing capacity without introducing additional bias. Extensive experiments on three real-world recommendation datasets demonstrate that our methods improve the causal balancing capability of learned propensities and enhance debiasing performance.
Förderung
- National Natural Science Foundation of China
- ARC
Zitieren
APA
Wang, H., Chen, Z., Zhang, H., Li, Z., Pan, L., Li, H., & Gong, M. (2025). Debiased Recommendation via Wasserstein Causal Balancing. ACM Transactions on Information Systems, 43(6), 1-24. https://doi.org/10.1145/3725731
Vancouver
Wang H, Chen Z, Zhang H, Li Z, Pan L, Li H, et al. Debiased Recommendation via Wasserstein Causal Balancing. ACM Transactions on Information Systems. 2025;43(6):1-24. doi:10.1145/3725731
BibTeX
@article{Wang2025,
author = {Wang, Hao and Chen, Zhichao and Zhang, Honglei and Li, Zhengnan and Pan, Licheng and Li, Haoxuan and Gong, Mingming},
title = {Debiased Recommendation via Wasserstein Causal Balancing},
journal = {ACM Transactions on Information Systems},
year = {2025},
volume = {43},
number = {6},
pages = {1--24},
doi = {10.1145/3725731}
}
EUVIMED